无回放的在线持续学习与自监督多补丁
Replay-free Online Continual Learning with Self-Supervised MultiPatches
AI总结：
针对在线持续学习（OCL）中回放策略因隐私限制无法使用的问题，提出持续多补丁（CMP）插件，通过生成单样本多补丁并投影到共享特征空间避免回放，性能优于回放及其他SSL策略。
摘要：
在线持续学习（OCL）方法在非平稳数据流上训练模型，每次仅提供少量样本，通常采用回放策略。然而，回放的使用有时被禁止，尤其是在有严格隐私法规的应用中。因此，我们提出持续多补丁（CMP），这是一种有效的插件，适用于现有OCL自监督学习策略，可避免使用回放样本。CMP从单个样本生成多个补丁，并将它们投影到共享特征空间，使来自同一示例的补丁被推到一起而不会坍缩到单个点。CMP在OCL流上优于回放和其他基于SSL的策略，挑战了回放作为自监督OCL首选解决方案的角色。
英文摘要：
Online Continual Learning (OCL) methods train a model on a non-stationary data stream where only a few examples are available at a time, often leveraging replay strategies. However, usage of replay is sometimes forbidden, especially in applications with strict privacy regulations. Therefore, we propose Continual MultiPatches (CMP), an effective plug-in for existing OCL self-supervised learning strategies that avoids the use of replay samples. CMP generates multiple patches from a single example and projects them into a shared feature space, where patches coming from the same example are pushed together without collapsing into a single point. CMP surpasses replay and other SSL-based strategies on OCL streams, challenging the role of replay as a go-to solution for self-supervised OCL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
